pretrain_imitation.py [346:400]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            for k, v in train_metrics.items():
                train_metrics_tracker[k].append(v)

            for k, v in train_metrics_tracker.items():
                logging.info(f"{k}: {np.mean(v).item():.3f}")
                tbwriter.add_scalar(f"train_metrics/{k}", np.mean(v).item(), j)

        # =================== Evaluate models ====================
        if args.eval_interval is not None and (j + 1) % args.eval_interval == 0:
            if "habitat" in args.env_name:
                devices = [
                    int(dev) for dev in os.environ["CUDA_VISIBLE_DEVICES"].split(",")
                ]
                # Devices need to be indexed between 0 to N-1
                devices = [dev for dev in range(len(devices))]
                eval_envs = make_vec_envs_habitat(
                    args.eval_habitat_config_file, device, devices
                )
            else:
                eval_envs = make_vec_envs_avd(
                    args.env_name,
                    args.seed + 12,
                    12,
                    eval_log_dir,
                    device,
                    True,
                    split="val",
                    nRef=args.num_pose_refs,
                    set_return_topdown_map=True,
                )

            num_eval_episodes = 16 if "habitat" in args.env_name else 30

            eval_config = {}
            eval_config["num_steps"] = args.num_steps
            eval_config["feat_shape_sim"] = args.feat_shape_sim
            eval_config["num_processes"] = 1 if "habitat" in args.env_name else 12
            eval_config["num_pose_refs"] = args.num_pose_refs
            eval_config["num_eval_episodes"] = num_eval_episodes
            eval_config["env_name"] = args.env_name
            eval_config["actor_type"] = "learned_policy"
            eval_config["encoder_type"] = args.encoder_type
            eval_config["use_action_embedding"] = args.use_action_embedding
            eval_config["use_collision_embedding"] = args.use_collision_embedding
            eval_config[
                "vis_save_dir"
            ] = f"{args.save_dir}/policy_vis/update_{(j+1):05d}"
            models = {}
            models["encoder"] = encoder
            models["actor_critic"] = actor_critic
            val_metrics, _ = evaluate_visitation(
                models, eval_envs, eval_config, device, visualize_policy=False
            )
            for k, v in val_metrics.items():
                tbwriter.add_scalar(f"val_metrics/{k}", v, j)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



train_exploration.py [373:427]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            for k, v in train_metrics.items():
                train_metrics_tracker[k].append(v)

            for k, v in train_metrics_tracker.items():
                logging.info(f"{k}: {np.mean(v).item():.3f}")
                tbwriter.add_scalar(f"train_metrics/{k}", np.mean(v).item(), j)

        # =================== Evaluate models ====================
        if args.eval_interval is not None and (j + 1) % args.eval_interval == 0:
            if "habitat" in args.env_name:
                devices = [
                    int(dev) for dev in os.environ["CUDA_VISIBLE_DEVICES"].split(",")
                ]
                # Devices need to be indexed between 0 to N-1
                devices = [dev for dev in range(len(devices))]
                eval_envs = make_vec_envs_habitat(
                    args.eval_habitat_config_file, device, devices
                )
            else:
                eval_envs = make_vec_envs_avd(
                    args.env_name,
                    args.seed + 12,
                    12,
                    eval_log_dir,
                    device,
                    True,
                    split="val",
                    nRef=args.num_pose_refs,
                    set_return_topdown_map=True,
                )

            num_eval_episodes = 16 if "habitat" in args.env_name else 30

            eval_config = {}
            eval_config["num_steps"] = args.num_steps
            eval_config["feat_shape_sim"] = args.feat_shape_sim
            eval_config["num_processes"] = 1 if "habitat" in args.env_name else 12
            eval_config["num_pose_refs"] = args.num_pose_refs
            eval_config["num_eval_episodes"] = num_eval_episodes
            eval_config["env_name"] = args.env_name
            eval_config["actor_type"] = "learned_policy"
            eval_config["encoder_type"] = args.encoder_type
            eval_config["use_action_embedding"] = args.use_action_embedding
            eval_config["use_collision_embedding"] = args.use_collision_embedding
            eval_config[
                "vis_save_dir"
            ] = f"{args.save_dir}/policy_vis/update_{(j+1):05d}"
            models = {}
            models["encoder"] = encoder
            models["actor_critic"] = actor_critic
            val_metrics, _ = evaluate_visitation(
                models, eval_envs, eval_config, device, visualize_policy=False
            )
            for k, v in val_metrics.items():
                tbwriter.add_scalar(f"val_metrics/{k}", v, j)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -